Solving Inverse Problems in Medical Imaging with Score-Based Generative Models

TL;DR

This paper introduces an unsupervised score-based generative modeling approach for medical image reconstruction that generalizes well across different measurement processes in CT and MRI, outperforming traditional supervised methods.

Contribution

The authors develop a flexible, unsupervised reconstruction method using score-based models that does not rely on fixed measurement models during training, enhancing generalization.

Findings

Achieves comparable or better accuracy than supervised methods.

Demonstrates superior generalization to unseen measurement processes.

Applicable to both CT and MRI imaging tasks.

Abstract

Reconstructing medical images from partial measurements is an important inverse problem in Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). Existing solutions based on machine learning typically train a model to directly map measurements to medical images, leveraging a training dataset of paired images and measurements. These measurements are typically synthesized from images using a fixed physical model of the measurement process, which hinders the generalization capability of models to unknown measurement processes. To address this issue, we propose a fully unsupervised technique for inverse problem solving, leveraging the recently introduced score-based generative models. Specifically, we first train a score-based generative model on medical images to capture their prior distribution. Given measurements and a physical model of the measurement process at test time, we introduce a sampling method to reconstruct an image consistent with both the prior and the observed measurements. Our method does not assume a fixed measurement process during training, and can thus be flexibly adapted to different measurement processes at test time. Empirically, we observe comparable or better performance to supervised learning techniques in several medical imaging tasks in CT and MRI, while demonstrating significantly better generalization to unknown measurement processes.